| Method and apparatus for distributed analyses of images -> Monitor Keywords |
|
|
  Method and apparatus for distributed analyses of imagesUSPTO Application #: 20060140443Title: Method and apparatus for distributed analyses of images Abstract: A method and apparatus for intelligent distributed analyses of images including capturing the images and analyzing the captured images, where feature information is extracted from the captured images. The extracted feature information is used in determining whether a predefined condition is met, and the extracted feature information is transmitted for further analysis when the predefined condition is met. The extracted feature information is stored and is used to generate statistical information related to the extracted feature information. Further, additional feature information is provided from other databases to implement further analysis including an event detection or recognition. Accordingly, distributed intelligent analyses of images is provided for analyzing captured images to efficiently and effectively implement event detection or recognition. (end of abstract)
Agent: Agilent Technologies, Inc. Intellectual Property Administration, Legal Dept. - Loveland, CO, US Inventors: Richard L. Baer, John Stewart Wenstrand USPTO Applicaton #: 20060140443 - Class: 382103000 (USPTO) Related Patent Categories: Image Analysis, Applications, Target Tracking Or Detecting The Patent Description & Claims data below is from USPTO Patent Application 20060140443. Brief Patent Description - Full Patent Description - Patent Application Claims
BACKGROUND OF THE INVENTION Description of the Related Art [0001] As the use of images for event detection or recognition becomes more pervasive, efficient ways of analyzing images becomes essential. Generally, analyzing images for event detection or recognition consists of capturing the images and analyzing the captured images using human operators. For example, images of an entrance into a building or room captured by a video camera are maintained such that a human operator subsequently reviews the captured images to determine whether a person has entered the building or room. In this situation, the human operator must constantly monitor the captured images to determine an occurrence of an event or an existence of a condition, and a significant amount of captured images that need to be monitored must be transmitted from the video camera. [0002] A typical system for capturing and analyzing images requires that image signals be carried over dedicated coaxial cable, fiber optic line, etc., and further requires that electrical power be supplied to support continuous operation. Thus, the cost of the typical system is significant. [0003] Other solutions for image processing have been proposed where processing of captured images is implemented using a processor in an image capturing device such that an alert or an alarm is triggered when a change occurs. For example, an image capturing device, such a camera in front of a store, may be provided with a processor for processing images captured by the camera so that the camera triggers an alarm when a number of pixels between consecutive images exceeds a certain threshold. However, a processor installed on a camera has limited capability due to size, weight, cost, power limitations, etc., and thus, does not enable complex event detection or recognition. Further, due to the limited processing capability of the processor installed on the camera, accurate event detection or recognition can not be implemented, thereby increasing the rate of false alerts or alarms. [0004] Accordingly, it is important to provide intelligent distributed analyses of images for efficient event detection or recognition. This becomes especially important as image analysis continues to be necessitated by different purposes, such as for security purposes, etc. Thus, there is a need for intelligent distributed analyses of images that addresses the above-mentioned and other limitations. SUMMARY OF THE INVENTION [0005] Various embodiments of the present invention provide a method including (a) capturing digital image data by a sensor, (b) extracting feature information in real-time from the captured digital image data and determining whether the extracted feature information meets a predefined condition by the sensor, and (c) transmitting the extracted feature information to a remote device for further analysis when the sensor determines that that the extracted feature information meets the predefined condition. [0006] Various embodiments of the present invention provide an apparatus including (a) a sensor capturing images, and (b) a processor extracting feature information from the captured images, determining whether changes in the extracted feature information pass a threshold level and causing the extracted information to be sent to a remote device for further analysis when the processor determines that the changes pass the threshold level. [0007] Moreover, various embodiments of the present invention provide a distributed event detection apparatus including (a) a plurality of image sensors capturing image data and interpreting the captured image data to extract feature information from the captured image data, and (b) a server connected with the plurality of image sensors receiving the extracted feature information for further analysis including an event detection, where the plurality of image sensors transmit the extracted feature information of the captured image to the server when the extracted feature information meets a predefined condition. [0008] Various embodiments of the present invention provide present invention further provides a method including (a) capturing a plurality of low resolution digital images via multiple distributed sensors, (b) combining the captured plurality of low resolution digital images into a single high resolution digital image, and (c) extracting feature information from the high resolution digital image. BRIEF DESCRIPTION OF THE DRAWINGS [0009] These and/or other aspects and advantages of the invention will become apparent and more readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which: [0010] FIG. 1 is a diagram illustrating a process of capturing images, extracting feature information from the captured images, determining whether the extracted feature information meets a predefined condition and transmitting the extracted feature information for further analysis, according to an embodiment of the present invention. [0011] FIG. 2 is a diagram illustrating an apparatus for capturing images, interpreting the captured images to extract feature information from the captured images and sending the extracted information for further analysis, according to an embodiment of the present invention. [0012] FIG. 3 is a diagram illustrating a process for multiple levels of event detection or recognition, according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS [0013] Reference will now be made in detail to the present embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to the like elements throughout. The embodiments are described below to explain the present invention by referring to the figures. [0014] FIG. 1 is a diagram illustrating a process 100 for capturing images, extracting feature information from the captured images, determining whether the extracted feature information meets a predefined condition and transmitting the extracted feature information from the captured images for further analysis, according to an embodiment of the present invention. Referring to FIG. 1, in operation 10, images are captured. For example, according to an embodiment of the present invention, still images are captured using a sensor. The present invention, however, is not limited to using one sensor. Instead, multiple sensors may be provided to capture still images. Moreover, the present invention is not limited to the captured images being "still" images. [0015] It is well known how to capture an image. The image may be captured using a sensor such as, for example, a digital camcorder, a digital still camera, a cellular telephone, a personal digital assistant, or other devices responsive to a particular motion, sound, light, etc. Generally, these sensors incorporate an image capturing device, typically a charge coupled device (CCD) or a CMOS image sensor (CIS), that registers the image, and image processing hardware and/or software that converts a raw signal produced by the image sensor to useful image data, such as CCIR or JPEG data. However, the present invention is not limited to any particular type of sensor. [0016] Referring to FIG. 1, from operation 10, the process 100 moves to operation 12, where feature information is extracted from the captured images. The feature information can be extracted using various methods, and thus, the present invention is not limited to any specific method of extracting feature information from captured images. For example, the present invention can be set up to extract essential feature information related to relative brightness or chromaticity values of images to detect a change between the brightness or chromaticity values of images. Further, an algorithm can be used to determine when a change has occurred, for example, by computing a difference between consecutive images based on a count of a number of pixels in the images and indicating when the difference exceeds a certain value. Various feature information extraction methods are well known. [0017] From operation 12, the process 100 moves to operation 14, where it is determined whether the extracted feature information meets a predefined condition. For example, according to an embodiment of the present invention, it is determined whether a change has occurred based on a difference computed between a number of pixels in consecutive images using an algorithm. In this situation, the change based on the difference computed between the number of pixels in the images is the predefined condition. However, the present invention is not limited to a predefined condition determined based on a difference between computed number of pixels. [0018] From operation 14, the process 100 moves to operation 16, where the extracted feature information is transmitted for further analysis when the extracted feature information meets the predefined condition. For example, in relation to the example discussed in the previous paragraph, the extracted information is transmitted for further analysis upon determining that the change has occurred based on the difference computed between the number of pixels in the images. Further, according to an embodiment of the present invention, the transmitted feature information includes, for example, a single image or a small number of images. [0019] The present invention is not limited to a particular number of subsequent analyses of feature information. For example, upon determining that the change has occurred based on the difference computed between the number of pixels in the images and transmitting the feature information, it is possible to further transmit the feature information for other subsequent analysis. Continue reading... Full patent description for Method and apparatus for distributed analyses of images Brief Patent Description - Full Patent Description - Patent Application Claims Click on the above for other options relating to this Method and apparatus for distributed analyses of images patent application. ###  How KEYWORD MONITOR works... a FREE service from FreshPatents1. Sign up (takes 30 seconds). 2. Fill in the keywords to be monitored. 3. Each week you receive an email with patent applications related to your keywords. Start now! - Receive info on patent apps like Method and apparatus for distributed analyses of images or other areas of interest. ### Previous Patent Application: Method and apparatus for capturing digital facial images optimally suited for manual and automated recognition Next Patent Application: Apparatus and method for detecting vehicle Industry Class: Image analysis ### FreshPatents.com Support Thank you for viewing the Method and apparatus for distributed analyses of images patent info. IP-related news and info Results in 0.22299 seconds Other interesting Feshpatents.com categories: Accenture , Agouron Pharmaceuticals , Amgen , AT&T , Bausch & Lomb , Callaway Golf |
||
